An integrated intelligent terminal control system for customized image material sales

Abstract

This invention relates to the field of integrated image customization and intelligent sales decision-making technology, specifically to an integrated image customization material sales intelligent terminal control system. The system includes an intelligent terminal main control center for retrieving image data to be printed and user-selected material inventory unit information; an image reproduction complexity modeling unit for generating an image reproduction complexity index; a material medium interference potential analysis unit for generating a material medium interference potential; a process feasibility coupling calculation unit for calculating the process feasibility probability; and a dynamic sales decision reconstruction unit for comparing the process feasibility probability with a preset benchmark pass rate threshold. If the process feasibility probability is less than the preset benchmark pass rate threshold, a dynamic risk premium instruction is generated; otherwise, a basic selling price maintenance instruction is generated. This invention ensures that the control strategy can be dynamically optimized as equipment status ages or model changes, solving the problem that static models are difficult to adapt to dynamic performance changes in equipment.

Description

Technical Field

[0001] This invention relates to the field of integrated image customization and intelligent sales decision-making technology, specifically to an integrated intelligent terminal control system for image customization material sales. Background Technology

[0002] The integrated intelligent terminal control system for image customization material sales aims to solve the problem of how to make dynamic and accurate sales pricing decisions based on the complexity of the image to be printed and the characteristics of the selected materials, combined with the real-time status of the terminal equipment, in image customization services.

[0003] In existing technologies, the pricing of customized image materials may mainly rely on fixed cost accounting or empirical rules, lacking a quantitative assessment of the feasibility of the printing process. This approach is difficult to adapt to the varying complexity of printing tasks, the different precision requirements of printing equipment for different image data, and the high complexity of images, which can easily lead to defects. The physical properties of the materials can hinder image quality and affect the yield rate of finished products. Furthermore, the real-time status of the equipment determines the current process tolerance, and the risk of printing failure increases when performance degrades. Due to the lack of a closed-loop control architecture that integrates hardware and software, existing systems cannot couple the characteristics of images, materials, and equipment to calculate the probability of process feasibility. Therefore, it is difficult to assess risks in advance before printing and generate dynamic risk premium instructions in a timely manner to reasonably offset the reprint costs caused by high-difficulty tasks or poor equipment status, thereby ensuring economic benefits and customer experience. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an integrated intelligent terminal control system for the sale of customized image materials. Specifically, the technical solution of this invention includes:

[0005] The intelligent terminal main control center is used to respond to user interaction commands and retrieve the image data to be printed and the material inventory unit information selected by the user.

[0006] The image reproduction complexity modeling unit is used to extract features and calculate entropy values ​​from the image data to be printed, and to generate an image reproduction complexity index.

[0007] The material medium interference potential analysis unit is used to map the physical properties of the material inventory unit information and generate the material medium interference potential.

[0008] The process feasibility coupling calculation unit is used to obtain the process tolerance index of the current terminal physical equipment, and combine the image reproduction complexity index and the material medium interference potential to calculate the process feasibility probability using the logistic function.

[0009] The dynamic sales decision reconstruction unit is used to obtain a preset benchmark pass rate threshold and compare the probability of process feasibility with the preset benchmark pass rate threshold.

[0010] If the probability of process feasibility is less than the preset benchmark pass rate threshold, a dynamic risk premium instruction is generated.

[0011] If the probability of process feasibility is greater than or equal to the preset benchmark pass rate threshold, a basic selling price maintenance instruction is generated.

[0012] Optionally, the image reproduction complexity modeling unit performs the following steps:

[0013] The image data to be printed is converted into a single-channel grayscale matrix, and the pixel intensity values ​​of the single-channel grayscale matrix are normalized to a preset range to generate a normalized image matrix.

[0014] The local standard deviation matrix is ​​obtained by performing a sliding window calculation on the normalized image matrix. The arithmetic mean of the local standard deviation matrix is ​​calculated to generate the global mean of image texture intensity.

[0015] The arithmetic mean of the normalized image matrix is ​​used to generate the global average brightness value of the image.

[0016] The inverse of the signal-to-noise ratio is calculated based on the global mean of image texture intensity, the global average brightness value of the image, and the preset minimum normal value.

[0017] Calculate the Shannon entropy value of the normalized image matrix;

[0018] The image reproduction complexity index is generated by weighted summation of the reciprocal of the signal-to-noise ratio and the Shannon entropy value.

[0019] Optionally, the material medium interference potential analysis unit performs the following steps:

[0020] Obtain the surface arithmetic mean roughness value and substrate absorbance value corresponding to the unit information of material inventory;

[0021] Calculate the ratio of the surface arithmetic mean roughness value to the preset limit roughness constant, and generate a roughness interference term;

[0022] Calculate the ratio of the substrate absorbance value to the preset optical density limit constant to generate an optical density interference term;

[0023] By using preset influence factor weights, the roughness interference term and the optical density interference term are weighted and summed to generate the material medium interference potential.

[0024] Optionally, the process feasibility coupling calculation unit performs the following steps:

[0025] Collect real-time physical sensor data of the current terminal physical device, and generate a process tolerance index based on the real-time physical sensor data;

[0026] Calculate the product of the image reproduction complexity index and the material medium interference potential to generate a coupling conflict value;

[0027] Calculate the difference between the coupling conflict value and the process tolerance index to generate the net risk value;

[0028] Based on the preset discrimination sensitivity coefficient and net risk value, the probability of process feasibility is calculated using the logistic function.

[0029] Optionally, the dynamic sales decision refactoring unit performs the following steps:

[0030] When a dynamic risk premium instruction is generated, the difference between the preset benchmark pass rate threshold and the probability of process feasibility is calculated.

[0031] Calculate the product of the difference and the preset risk premium coefficient to generate the premium range;

[0032] Obtain the base selling price corresponding to the unit information of material inventory, and calculate the dynamic selling price based on the base selling price and the premium range;

[0033] When a base price maintenance instruction is generated, the base price is directly marked as the dynamic price.

[0034] Optional, real-time physical sensor data may include nozzle clogging rate data or laser power data;

[0035] When nozzle blockage rate data is collected, the difference between value 1 and nozzle blockage rate data is calculated to generate process tolerance index.

[0036] When laser power data is acquired, a preset mapping function is used to transform the laser power data and generate a process tolerance index.

[0037] Optionally, it also includes a weight adaptive adjustment module, which performs the following steps:

[0038] Identify the printing device type of the current terminal physical device;

[0039] If the printing device is a dye-sublimation printer, increase the weighting coefficient corresponding to the inverse of the signal-to-noise ratio;

[0040] If the printing device is a laser engraving machine, increase the weighting coefficient corresponding to the Shannon entropy value.

[0041] Optionally, the steps for setting the preset impact factor weights are as follows:

[0042] Identify the process contact type of the current terminal physical equipment;

[0043] If the process contact type is a contact process, set the weighting coefficient of the roughness interference item to be greater than the weighting coefficient of the optical density interference item.

[0044] If the process contact type is non-contact inkjet process, set the weight coefficient of the optical density interference item to be greater than the weight coefficient of the roughness interference item.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. This system realizes quantitative assessment and closed-loop control of printing risks; by constructing a mathematical model of image reproduction complexity and material medium interference potential energy, and combining it with the real-time process tolerance of the equipment, the probability of process feasibility is calculated using logistic functions; this overcomes the blindness of existing technologies that rely solely on experience or fixed cost accounting, and establishes a closed-loop architecture of hardware and software collaboration, which can accurately quantify the success rate of matching images, materials and equipment before production, effectively reducing the risk of scrap caused by blind production;

[0047] 2. This system establishes a dynamic pricing mechanism based on objective process risks; it not only assesses risks but also constructs dynamic sales decision logic; by comparing the probability of process feasibility with the benchmark pass rate threshold, it automatically generates risk premium instructions for high-risk tasks and maintains the base price for low-risk tasks; this mechanism can reasonably offset the potential reprint costs caused by high-difficulty images or special materials, solve the problem of profit inversion in complex customization scenarios under the traditional fixed pricing model, and ensure operating efficiency;

[0048] 3. This system improves the resolution accuracy of heterogeneous materials and complex images; it adopts a multi-dimensional feature extraction method, comprehensively assessing the reproduction difficulty by considering texture intensity and information entropy at the image level, and mapping surface roughness and absorbance into physical interference potential energy at the material level; this fine-grained physical property mapping mechanism fully considers the hindering effect of material surface characteristics on imaging quality, avoids the one-sidedness of single-dimensional evaluation, and significantly improves the system's adaptability to various non-standard customized materials.

[0049] 4. This system has the ability to perceive equipment status and adapt the model to change its operating conditions. By collecting real-time sensor data such as nozzle blockage rate or laser power, it dynamically updates the process tolerance index to reflect the current performance of the equipment. At the same time, the system can adaptively adjust the weight coefficients in the calculation model according to the equipment type and contact method. This ensures that the control strategy can be dynamically optimized as the equipment status ages or the model changes, solving the problem that static models are difficult to adapt to changes in the dynamic performance of the equipment. Attached Figure Description

[0050] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0051] Figure 1 This is a structural diagram of the system of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0053] Example 1:

[0054] Please see Figure 1 An integrated intelligent terminal control system for customized image-based sales materials includes:

[0055] The intelligent terminal main control center is used to respond to user interaction commands and retrieve the image data to be printed and the material inventory unit information selected by the user.

[0056] The image reproduction complexity modeling unit is used to extract features and calculate entropy values ​​from the image data to be printed, and to generate an image reproduction complexity index.

[0057] The material medium interference potential analysis unit is used to map the physical properties of the material inventory unit information and generate the material medium interference potential.

[0058] The process feasibility coupling calculation unit is used to obtain the process tolerance index of the current terminal physical equipment, and combine the image reproduction complexity index and the material medium interference potential to calculate the process feasibility probability using the logistic function.

[0059] The dynamic sales decision reconstruction unit is used to obtain a preset benchmark pass rate threshold and compare the probability of process feasibility with the preset benchmark pass rate threshold.

[0060] If the probability of process feasibility is less than the preset benchmark pass rate threshold, a dynamic risk premium instruction is generated.

[0061] If the probability of process feasibility is greater than or equal to the preset benchmark pass rate threshold, a basic selling price maintenance instruction is generated.

[0062] An integrated intelligent terminal control system for customized image-based material sales is implemented through a closed-loop control architecture that integrates hardware and software. The system includes an intelligent terminal main control center, an image reproduction complexity modeling unit, a material medium interference potential analysis unit, a process feasibility coupling calculation unit, and a dynamic sales decision reconstruction unit. The intelligent terminal main control center is equipped with a data bus interface to respond to user interaction commands and retrieve the image data to be printed and the material inventory quantity unit information selected by the user in real time. The image reproduction complexity modeling unit performs feature extraction and entropy calculation on the image data to be printed, generating a dimensionless image reproduction complexity index. This index characterizes the level of image accuracy required by printing equipment; the material medium interference potential analysis unit maps the physical properties of the material inventory unit information to generate the material medium interference potential. This characterizes the hindering effect of material surface properties on imaging quality; the process feasibility coupling calculation unit obtains the process tolerance index of the current terminal physical equipment. Combined with the image reproduction complexity index Interference potential with material medium The probability of process feasibility is calculated using the logistic function. The dynamic sales decision reconstruction unit obtains the preset benchmark pass rate threshold. The probability of process feasibility Compare with this threshold; if the probability of process feasibility is... Less than the preset benchmark pass rate threshold Generate dynamic risk premium orders; if the probability of process feasibility... Greater than or equal to the preset benchmark pass rate threshold Generate a base price maintenance order.

[0063] Example 2:

[0064] The image reproduction complexity modeling unit performs the following steps:

[0065] The image data to be printed is converted into a single-channel grayscale matrix, and the pixel intensity values ​​of the single-channel grayscale matrix are normalized to a preset range to generate a normalized image matrix.

[0066] The local standard deviation matrix is ​​obtained by performing a sliding window calculation on the normalized image matrix. The arithmetic mean of the local standard deviation matrix is ​​calculated to generate the global mean of image texture intensity.

[0067] The arithmetic mean of the normalized image matrix is ​​used to generate the global average brightness value of the image.

[0068] The inverse of the signal-to-noise ratio is calculated based on the global mean of image texture intensity, the global average brightness value of the image, and the preset minimum normal value.

[0069] Calculate the Shannon entropy value of the normalized image matrix;

[0070] The image reproduction complexity index is generated by weighted summation of the reciprocal of the signal-to-noise ratio and the Shannon entropy value.

[0071] The image reproduction complexity modeling unit converts the image data to be printed into a single-channel grayscale matrix. The pixel intensity values ​​of the matrix are normalized to a preset range to generate a normalized image matrix; a sliding window calculation is then performed on the normalized image matrix to obtain the local standard deviation matrix. Calculate the arithmetic mean of the local standard deviation matrix to generate the global mean of image texture intensity. ; Calculate the arithmetic mean of the normalized image matrix to generate the global average brightness value of the image. Based on the global mean of image texture intensity Global average brightness value of the image and preset minimum normal number Calculate the reciprocal of the signal-to-noise ratio; calculate the Shannon entropy of the normalized image matrix. ; the reciprocal of the signal-to-noise ratio and the Shannon entropy value Perform a weighted summation to generate the image reproduction complexity index. ;

[0072] Weighting coefficients here and The value is determined through a pre-built calibration process; the construction includes... A calibration dataset of standard sample images. Record the actual defect rate of each sample image under standard printing conditions. and the corresponding calibrated texture intensity and calibration entropy value Establishment through multiple regression analysis , and The mapping relationship between them is used to calculate the factor that minimizes the model's prediction error. and The value is calculated using the following formula:

[0073]

[0074] in Values To prevent the denominator from being zero.

[0075] Example 3:

[0076] The material medium interference potential analysis unit performs the following steps:

[0077] Obtain the surface arithmetic mean roughness value and substrate absorbance value corresponding to the unit information of material inventory;

[0078] Calculate the ratio of the surface arithmetic mean roughness value to the preset limit roughness constant, and generate a roughness interference term;

[0079] Calculate the ratio of the substrate absorbance value to the preset optical density limit constant to generate an optical density interference term;

[0080] By using preset influence factor weights, the roughness interference term and the optical density interference term are weighted and summed to generate the material medium interference potential.

[0081] The material medium interference potential analysis unit retrieves the surface arithmetic mean roughness value corresponding to the material inventory unit information from the preset database. and substrate absorbance value ; Calculate the arithmetic mean surface roughness value With the preset limit roughness constant The ratio is used to generate a roughness interference term; the substrate absorbance value is calculated. With respect to the preset optical density limit constant The ratio is used to generate an optical density interference term; the preset influence factor weights are then used. and The roughness interference term and the optical density interference term are weighted and summed to generate the material medium interference potential. The specific calculation formula is as follows:

[0082]

[0083] This represents the physical limit of roughness allowed by current printing technology. It is the optical density limiting constant.

[0084] Example 4:

[0085] The process feasibility coupling calculation unit performs the following steps:

[0086] Collect real-time physical sensor data of the current terminal physical device, and generate a process tolerance index based on the real-time physical sensor data;

[0087] Calculate the product of the image reproduction complexity index and the material medium interference potential to generate a coupling conflict value;

[0088] Calculate the difference between the coupling conflict value and the process tolerance index to generate the net risk value;

[0089] Based on the preset discrimination sensitivity coefficient and net risk value, the probability of process feasibility is calculated using the logistic function.

[0090] The process feasibility coupling calculation unit collects real-time physical sensor data from the current terminal physical equipment and generates a process tolerance index based on the real-time physical sensor data. The range of values ​​for this index is strictly limited to... Within the range;

[0091] To ensure consistency in computational dimensions, the system introduces a preset system load normalization coefficient. ; Calculate the complexity index of image reproduction Interference potential with material medium The product of the two, and using the system load normalization coefficient. The product is scaled to generate a normalized load index. Normalized load index Used to characterize the pressure level of the current printing task relative to the theoretical limit of the device;

[0092] Calculate the normalized load index With process tolerance index The difference is used to generate the net risk value. Based on preset discrimination sensitivity coefficients and net risk value The probability of process feasibility is calculated using the logistic function. This calculation process ensures the accuracy of the probabilistic evaluation model's nonlinear response in the edge regions of equipment performance by unifying task load and equipment capability to the same dimension range. The specific calculation formula is as follows:

[0093]

[0094]

[0095] In the formula, This is the system load normalization factor, whose value is the theoretical maximum load value of the system. The reciprocal of, among which Calculations are made based on the bit depth and texture limits of the image data, specifically... The theoretical maximum value after weighting is calculated using the following formula: For an 8-bit grayscale image, the theoretical maximum entropy is 8, and the maximum texture intensity is 0.5. The sum of the material disturbance potential weighting coefficients This coefficient is used to map task load to The space is designed to match the dimensions of the process tolerance index; The dimensionless constant used to control the steepness of the S-curve is determined by the inherent error conversion bandwidth of the equipment.

[0096] Example 5:

[0097] The dynamic sales decision restructuring unit performs the following steps:

[0098] When a dynamic risk premium instruction is generated, the difference between the preset benchmark pass rate threshold and the probability of process feasibility is calculated.

[0099] Calculate the product of the difference and the preset risk premium coefficient to generate the premium range;

[0100] Obtain the base selling price corresponding to the unit information of material inventory, and calculate the dynamic selling price based on the base selling price and the premium range;

[0101] When a base price maintenance instruction is generated, the base price is directly marked as the dynamic price.

[0102] When the dynamic sales decision refactoring unit generates a dynamic risk premium instruction, it calculates a preset benchmark pass rate threshold. Probability of process feasibility The difference; calculate the difference and the preset risk premium coefficient. The product of these factors generates the premium margin; the base selling price corresponding to the unit inventory information of the material is obtained. Based on the base price Calculate the dynamic selling price with the premium. When a base price maintenance order is generated, the base price will be... Directly marked as dynamic price To ensure the consistency of the calculation logic and prevent price inversions for high-quality printed products, the specific calculation formula introduces a boundary constraint function as follows:

[0103]

[0104] This formula ensures that the probability of process feasibility is... Greater than or equal to the baseline threshold At that time, the premium item is automatically reset to zero, and the system only outputs the base price; among which, The coefficient is set based on the ratio of historical average reprint cost to average order value.

[0105] Example 6:

[0106] Real-time physical sensor data includes nozzle clogging rate data or laser power data;

[0107] When nozzle blockage rate data is collected, the difference between value 1 and nozzle blockage rate data is calculated to generate process tolerance index.

[0108] When laser power data is acquired, a preset mapping function is used to transform the laser power data and generate a process tolerance index.

[0109] Real-time physical sensor data includes nozzle clogging rate data. or laser power data When the nozzle clogging rate data is collected At that time, calculate the value 1 and the nozzle clogging rate data. The difference, the production process tolerance index Preset mapping function Configured as a negative correlation mapping, i.e., laser power data A higher value indicates that the equipment's output power is nearing its limit or the laser is severely aging, corresponding to a higher process tolerance index. The lower the value, the higher the efficiency; conversely, the lower the power value, the more the equipment is in a light-load, high-efficiency range, indicating a higher process tolerance index. The higher the value, the better; when laser power data is collected. At that time, use the preset mapping function laser power data Perform the conversion to generate the process tolerance index. .

[0110] Example 7:

[0111] This system also includes a weight adaptive adjustment module, which performs the following steps:

[0112] Identify the printing device type of the current terminal physical device;

[0113] If the printing device is a dye-sublimation printer, increase the weighting coefficient corresponding to the inverse of the signal-to-noise ratio;

[0114] If the printing device is a laser engraving machine, increase the weighting coefficient corresponding to the Shannon entropy value.

[0115] The weight adaptive adjustment module identifies the printing device type of the current terminal physical device; if the printing device type is a dye-sublimation printer, the weight coefficient corresponding to the reciprocal of the signal-to-noise ratio is increased. To increase the suppression weight for low signal-to-noise ratio features; if the printing device is a laser engraving machine, increase the weight coefficient corresponding to the Shannon entropy value. To focus on information content assessment.

[0116] Example 8:

[0117] The steps for setting the preset impact factor weights are as follows:

[0118] Identify the process contact type of the current terminal physical equipment;

[0119] If the process contact type is a contact process, set the weighting coefficient of the roughness interference item to be greater than the weighting coefficient of the optical density interference item.

[0120] If the process contact type is non-contact inkjet process, set the weight coefficient of the optical density interference item to be greater than the weight coefficient of the roughness interference item.

[0121] Preset impact factor weights and The settings are determined based on the process contact type of the current terminal physical equipment; if the process contact type is a contact process, the weighting coefficient of the roughness interference term is set. The weighting factor is greater than that of the optical density interference term. If the process contact type is non-contact inkjet printing, set the weighting coefficient for the optical density interference term. The weighting coefficient of the roughness interference term is greater than that of the roughness interference term. .

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An integrated intelligent terminal control system for customized image-based sales materials, characterized in that, include: The intelligent terminal main control center is used to respond to user interaction commands and retrieve the image data to be printed and the material inventory unit information selected by the user. The image reproduction complexity modeling unit is used to extract features and calculate entropy values ​​from the image data to be printed, and to generate an image reproduction complexity index. The material medium interference potential analysis unit is used to map the physical properties of the material inventory unit information and generate the material medium interference potential. The process feasibility coupling calculation unit is used to obtain the process tolerance index of the current terminal physical equipment, and combine the image reproduction complexity index and the material medium interference potential to calculate the process feasibility probability using the logistic function. The dynamic sales decision reconstruction unit is used to obtain a preset benchmark pass rate threshold and compare the probability of process feasibility with the preset benchmark pass rate threshold. If the probability of process feasibility is less than the preset benchmark pass rate threshold, a dynamic risk premium instruction is generated. If the probability of process feasibility is greater than or equal to the preset benchmark pass rate threshold, a basic selling price maintenance instruction is generated. The image reproduction complexity modeling unit performs the following steps: The image data to be printed is converted into a single-channel grayscale matrix, and the pixel intensity values ​​of the single-channel grayscale matrix are normalized to a preset range to generate a normalized image matrix. The local standard deviation matrix is ​​obtained by performing a sliding window calculation on the normalized image matrix. The arithmetic mean of the local standard deviation matrix is ​​calculated to generate the global mean of image texture intensity. The arithmetic mean of the normalized image matrix is ​​used to generate the global average brightness value of the image. The inverse of the signal-to-noise ratio is calculated based on the global mean of image texture intensity, the global average brightness value of the image, and the preset minimum normal value. Calculate the Shannon entropy value of the normalized image matrix; The image reproduction complexity index is generated by weighted summation of the inverse signal-to-noise ratio term and the Shannon entropy value. The material medium interference potential analysis unit performs the following steps: Obtain the surface arithmetic mean roughness value and substrate absorbance value corresponding to the unit information of material inventory; Calculate the ratio of the surface arithmetic mean roughness value to the preset limit roughness constant, and generate a roughness interference term; Calculate the ratio of the substrate absorbance value to the preset optical density limit constant to generate an optical density interference term; By using preset influence factor weights, the roughness interference term and the optical density interference term are weighted and summed to generate the material medium interference potential; The process feasibility coupling calculation unit performs the following steps: Collect real-time physical sensor data of the current terminal physical device, and generate a process tolerance index based on the real-time physical sensor data; Calculate the product of the image reproduction complexity index and the material medium interference potential to generate a coupling conflict value; Calculate the difference between the coupling conflict value and the process tolerance index to generate the net risk value; Based on the preset discrimination sensitivity coefficient and net risk value, the probability of process feasibility is calculated using the logistic function.

2. The integrated intelligent terminal control system for customized image material sales according to claim 1, characterized in that, The dynamic sales decision reconstruction unit performs the following steps: When a dynamic risk premium instruction is generated, the difference between the preset benchmark pass rate threshold and the probability of process feasibility is calculated. Calculate the product of the difference and the preset risk premium coefficient to generate the premium range; Obtain the base selling price corresponding to the unit information of material inventory, and calculate the dynamic selling price based on the base selling price and the premium range; When a base price maintenance instruction is generated, the base price is directly marked as the dynamic price.

3. The integrated intelligent terminal control system for customized image material sales according to claim 1, characterized in that, The real-time physical sensor data includes nozzle clogging rate data or laser power data; When nozzle blockage rate data is collected, the difference between value 1 and nozzle blockage rate data is calculated to generate process tolerance index. When laser power data is acquired, a preset mapping function is used to transform the laser power data and generate a process tolerance index.

4. The integrated intelligent terminal control system for customized image material sales according to claim 1, characterized in that, It also includes a weight adaptive adjustment module, which performs the following steps: Identify the printing device type of the current terminal physical device; If the printing device is a dye-sublimation printer, increase the weighting coefficient corresponding to the inverse of the signal-to-noise ratio; If the printing device is a laser engraving machine, increase the weighting coefficient corresponding to the Shannon entropy value.

5. The integrated intelligent terminal control system for customized image material sales according to claim 1, characterized in that, The steps for setting the preset impact factor weights are as follows: Identify the process contact type of the current terminal physical equipment; If the process contact type is a contact process, set the weighting coefficient of the roughness interference item to be greater than the weighting coefficient of the optical density interference item. If the process contact type is non-contact inkjet process, set the weight coefficient of the optical density interference item to be greater than the weight coefficient of the roughness interference item.

Images